telnyx-voice-streaming-ruby

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill utilizes the official telnyx Ruby gem for interacting with the vendor's API, which is an expected and verified dependency for this integration.
  • [SAFE]: Sensitive credentials are appropriately managed using environment variables (ENV["TELNYX_API_KEY"]), adhering to industry standards for secret management and avoiding hardcoded API keys.
  • [SAFE]: The skill promotes secure webhook handling by providing explicit examples for verifying Ed25519 signatures via the client.webhooks.unwrap method, protecting against spoofing attacks.
  • [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface by processing real-time transcription data from external phone calls, though the risk is minimal given the specialized nature of the tool.
  • Ingestion points: The skill ingests untrusted data through the call.transcription webhook events and WebSocket audio streams.
  • Boundary markers: The implementation includes strong boundary verification through mandatory Ed25519 signature validation on incoming webhook payloads.
  • Capability inventory: The skill's capabilities are limited to Telnyx call control actions (start/stop streaming, fork, transcribe) and does not execute arbitrary shell commands or access the host file system.
  • Sanitization: Data is processed through the official SDK which handles JSON parsing and payload structure validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 06:27 PM
Security Audit — agent-trust-hub — telnyx-voice-streaming-ruby